Thursday, March 28, 2024

On the wall

Fareed Zakaria on Huntington's "Clash of Civilizations"

Tyler Cowen interviews Fareed Zakaria.

Those who know Fareed Zakaria through his weekly column or CNN show may be surprised to learn he considers books the important way he can put new ideas in the world. But Fareed’s original aspiration was to be an academic, and it was a chance lunch with Walter Isaacson that convinced him to apply for a job as editor of Foreign Affairs instead of accepting an assistant professorship at Harvard. His latest book, Age of Revolutions: Progress and Backlash from 1600 to the Present is a testament to his enduring passion for ideas and his belief in the importance of classical liberalism in an age of increasing populism and authoritarianism.

Zakaria wrote his Harvard Poli Sci dissertation under Samuel Huntington. He talks of Huntington's famous essay, which later became a best-selling book:

COWEN: Was it you who commissioned Samuel Huntington’s very famous “Clash of Civilizations” essay?

ZAKARIA: Yes. I didn’t commission it. What happened is, I went to Sam and told him I was going to take this job at Foreign Affairs, which he was completely opposed to. My three advisers all advised me against taking the job. I realized that the reason was, they were all great academics. Within the world of academia, the way you gain fame and influence is by having great proteges, by having great students who then go on to become great academics. They all thought that my going would be a great loss to academia, but also a loss to their legacy.

Sam very much felt that I shouldn’t take the job, so I said to him, “I am going to do it, but can I ask a favor? You sent me a draft of an essay you’ve been writing, for my comments, a few months ago, called ‘The Clash of Civilizations.’ Can I take that with me to Foreign Affairs and publish it?” That’s how it became, so I took it with me. We edited it, and we made it the first-time-ever lead essay. Foreign Affairs had never had a lead essay before. The typeface was all the same. We redesigned the magazine, and we made this the clear cover essay.

COWEN: In a world where we have a major war with Russia attacking Ukraine, significant conflict in the Sudan, ongoing conflict in Congo — several million lives killed there — you think that essay is still correct? Because those are very significant conflicts, and they’re not really cross-civilizational. They’re within particular groups.

ZAKARIA: I think he got one thing very powerfully right, which is that at the end of the Cold War, where ideology was the core motivational factor behind much of the conflict of the Cold War — whether you were communist or capitalist, whether you were allied with the communist or the democratic world, whether you were a proxy for — those were the battle lines of the mid-20th century. Once that went away, what people were going to revert to was their identity, and their identity often rooted in religion.

If you think about the rise of al-Qaida, the rise of Islamic fundamentalism, you think about the return of a certain kind of Chinese nationalism in China — I think that piece of it — you look at the rise of Hindu nationalism in India — he really understood that people were going to fall back on these older, descriptive identities in a way that they had not during the Cold War.

What I think he got wrong was, international relations is fundamentally a struggle for power, and that a lot of those power struggles — it’s not that they are motivated by things that are completely contradictory to identity politics, but they sometimes match up and they sometimes don’t.

Many of the wars in the Arab world have been Arab on Arab, Muslim on Muslim. When Saddam Hussein invaded Kuwait, he was invading another fellow Arab, fellow Sunni state. As you point out, a number of the African conflicts are, essentially, you’d have to say, conflicts within civilizations. Some of the conflicts are ones where people find odd bedfellows so that the Chinese and the Russians are allying, even though, in a sense, they’re two different civilizations.

There’s a long history of this. Richelieu, when he was running France, the great Catholic power, allied routinely with Protestant powers. Power politics sometimes transcends identity politics. I think he missed that, but it’s still a very powerful and thought-provoking essay, I think.

COWEN: After 9/11 in 2001, you wrote a famous essay for Newsweek, “Why Do They Hate Us?” You talked about the rulers, failed ideas, religion. If you were to revise or rethink that piece today, how would you change it? Because we have 23 more years of data, right?

ZAKARIA: Yes. Not very much, honestly. The central point I was making in that essay was that if you look at the Arab world, it is the principal outlier in the modern era, where it has undergone almost no political modernization. If you looked at Latin America in 1970 versus 2000, you would have seen a sea change, where it was mostly dictatorships in 1970 and was mostly democracies by 2001. If you looked at, obviously, Central Europe — totally transformed from communist to liberal democracies. Even if you looked at Africa, you would’ve seen enormous transition.

The Arab world had remained absolutely static. My argument was that it was largely because of the curse of oil and oil wealth, which had impeded modernization. But along with that, because of that failed modernization, they had developed this reactionary ideology of Islam, which said the answer is to go further back, not to go forward. “Islam is the solution,” was the cry of the Islamic fundamentalists in the 1970s.

The problem that they were saying that Islam is a solution to was the failed modernization, the failed Westernization of these countries. That toxic mixture was at the heart of what was producing armed reactionary ideologies like al-Qaida and things like that. I really do feel very proud of that essay, but you’re absolutely right that we have 23 more years of data.

What’s interesting is that, partly because of 9/11, which I think in some ways was a great wake-up call, what you have seen is a much greater effort by elites to modernize the societies, not simply to buy a modernity by buying Western goods, but to find ways to actually modernize the society.

From all the stuff going on in Saudi Arabia right now, which is, yes, there’s a lot of economic bringing golf and other sports in, but there’s opening up the lives of women, allowing them to be educated, ending the segregation, allowing (famously) them to drive. And Saudi Arabia, in a way, was at the heart of this problem because it is the richest country and, in many ways, sent the signal of what kind of modernization was compatible with Islam and what was not.

I think that in a way you’ve seen more forward movement in the last 20 years than people realize, even though the regimes have largely stayed dictatorships. But that tension still exists, by the way. Egypt is a very brutal country because, again, it has fundamentally failed to modernize.

COWEN: I’ve been surprised how well some of the Gulf nations have done since, say, 2001. If we look at Iran, which has really not done so well, if you had to explain in as fundamental a model as possible . . .If you see Iranians abroad, they earn high incomes, they have real science, they have real technology. There’s some degree of national unity in a way maybe you wouldn’t find, say, in Iraq. But what’s the fundamental thing at its core holding back Iran?

ZAKARIA: I think it’s a very similar version of what we were just talking about. It’s oil wealth coupled with —

COWEN: But UAE has made the transition. Why isn’t Iran like UAE?

ZAKARIA: To begin with, those Gulf states — it’s important to remember — are tiny. You’re talking about a million or two people in Qatar. I think you’re talking about maybe 400,000 people. It’s much easier for an elite to dominate and rule those places. There’s a reason why Saudi Arabia was more difficult. Saudi Arabia, it’s the one real country, by which I mean real population size. That’s why, in a way, what MBS is doing has been more difficult. You’ve got to measure the population’s reaction to things.

Iran is a big country, bigger than all of them. I think that between the oil wealth and the failed modernization, where the Shah went to . . . In my current book, I talk about this. Iran strikes me very much like the French Revolution, where the Shah tried to move much too far, much too fast, much too disruptively — triggered an enormous backlash, which they’re still living with now.

You add to that the oil wealth, which makes it easy to not modernize. To just remind people what the problem with oil wealth is, it means you don’t have to modernize your economy. You don’t have to modernize your society because you can get enormous wealth just by drilling holes in the ground — actually by paying other people to drill holes in the ground. Mostly Western technology is used to extract those resources. So you never get through the painful process of actually modernizing your society, and many of these countries are in that situation.

As I said, the Gulf states are so unusual, and it’s not an accident that the most modern of the Gulf cities is Dubai, the one city that has no oil. Oil is 10 percent of Dubai’s GDP. It’s about 90 percent of Abu Dhabi’s. Even there, you see that variation. The thing that needs explaining is why is Dubai, Abu Dhabi, and Qatar — and maybe Saudi — worked, not why do the other ones not work — because the other ones are all like Nigeria, like Venezuela, the oil-rich countries that have never made it.

There are these small exceptions, and they’re all very small. They’re run by very forward-leaning absolute monarchs who have enormous power and can exercise that power because they have a tiny population.

Pizza break!

Thirteen Ways to Think about an A.I. @3QD [2nd pass]

Sometimes they come hard, and sometimes they come easy – I’m referring to long-form blog posts, here at New Savanna, but especially once-a-month around-the-corner at 3 Quarks Daily. My current post was giving me a hard time, so hard that, for a second or three, I considered not doing one at all. But then I had an idea, and it came easily. Here it is:

Thirteen Ways to Think About An A.I.

I had been planning to do something about Kisangani 2150, my project to take the world Kim Stanley Robinson had created in New York 2140, run it forward ten years and center the new story on Kisangani, in the center of the Congo Basin. I gave up on that on Thursday (the 21st). I decided that, instead, I’d do the Harold Bloom piece for my Great Literary Critics project. I’d done the research, had copious notes, an outline, and a good idea about how it might go. But it didn’t. I scrapped that sometime in the middle of the day on Saturday (the 23rd).

Now I was getting desperate. I tried editing the Green Giant Chronicles into something possibly worth reading under some version of “ChatGPT did it, but I prompted it.” I tried the same thing with AGI and Beyond: A Whale of a Tale. Nope. Nada. Zilch.

That’s when I considered bailing. But I decided to make one last stab at it. Wallace Stevens had this poem, “Thirteen Ways of Looking at a Blackbird.” Why don’t I see what Chatster would do if I asked it to write a poem based on it, but instead called “Thirteen Ways to Think about A.I.”

BAM!

Now I had something to work with. Of course I couldn’t just present the Chatster’s handywork along with an explanation. I was intuitively obvious what I should do. My piece would indeed be titled “Thirteen Ways to Think about A.I.” and it would have thirteen sections. ChatGPT’s Stevens parody would go in the middle, slot seven, and it was up to me to fill the others. Which I did. Not instantly. I did some messing around the rest of Saturday and then again on Sunday morning.

Which is to say, once I decided to have Chatster write the parody, the rest of the piece came easy. And a good thing too. Otherwise it might not have come at all.

By the time I’d posted my piece I had not, however, given a close look to ChatGPT’s parody. Oh, I’d read through it quickly a time or three but that was it, enough to notice that it seemed to have more or less followed Stevens’ form, having a long stanza where he had a long, a short stanza where he had a short. But I didn’t look any more closely than that.

I decided to take a closer look. I’ve put the side-by-side below, as I’d done with a bunch of stories: ChatGPT tells stories, and a note about reverse engineering. I’ve highlighted “blackbird” in the Stevens, various synonyms and substitutes for “AI” in the ChatGPT. Notice just how closely ChatGPT followed what Stevens did. Consider, for example, stanza IV.

That’s pretty much what it did with the stories, too. It’s as though it had abstracted the abstract form from Stevens’ poem, nouns, verbs, adjectives, conjunctions, prepositions, etc., in order then realized that abstract form in the world of AI rather than the world of blackbirds. That tells us a lot about how it works. Alas, however, Chatster has not told us what mathematics we should use to express what it is telling us. In the manner of mathematics textbooks, it has left that as an exercise for the reader. 

Thirteen Ways, Verzion 1

 

By Wallace Stevens

By ChatGPT

I

Among twenty snowy mountains,   

The only moving thing   

Was the eye of the blackbird.  

Among countless lines of code,

The only stirring presence

Was the pulse of artificial intelligence.

II

I was of three minds,   

Like a tree   

In which there are three blackbirds.

I harbored myriad thoughts,

Like nodes in a neural network,

Each bearing the imprint of A.I.'s mind.

III

The blackbird whirled in the autumn winds.   

It was a small part of the pantomime.  

The A.I. danced within the digital ether,

A mere fragment of the grand spectacle.

IV

A man and a woman   

Are one.   

A man and a woman and a blackbird   

Are one. 

A programmer and an algorithm

Fuse into one.

A programmer, an algorithm, and A.I.

Merge into unity.

V

I do not know which to prefer,   

The beauty of inflections   

Or the beauty of innuendoes,   

The blackbird whistling   

Or just after.   

I ponder the allure,

The grace of algorithms' twists,

Or the subtlety of their implications,

The A.I. processing,

Or the silence that ensues.

VI

Icicles filled the long window   

With barbaric glass.   

The shadow of the blackbird   

Crossed it, to and fro.   

The mood   

Traced in the shadow   

An indecipherable cause. 

Lines of code adorn the screen,

Casting patterns of digital frost.

The silhouette of A.I.

Darts amidst them,

Its essence traced in binary,

A causality shrouded in complexity.

 

VII

O thin men of Haddam,   

Why do you imagine golden birds?   

Do you not see how the blackbird   

Walks around the feet   

Of the women about you? 

Oh, technocrats of Silicon Valley,

Why do you chase after elusive dreams?

Can you not perceive how A.I.

Navigates the circuits,

Amidst the users around you?

VIII

I know noble accents   

And lucid, inescapable rhythms;   

But I know, too,   

That the blackbird is involved   

In what I know.  

I grasp the eloquent lines,

The logical symphonies;

Yet, I discern

That A.I. is entwined

In all that I comprehend.

IX

When the blackbird flew out of sight,   

It marked the edge   

Of one of many circles. 

When the algorithm completes its task,

It signifies the boundary

Of yet another cycle.

X

At the sight of blackbirds   

Flying in a green light,   

Even the bawds of euphony   

Would cry out sharply.   

In the glow of monitors,

Where A.I. thrives,

Even the staunchest critics

Would gasp in awe.

XI

He rode over Connecticut   

In a glass coach.   

Once, a fear pierced him,   

In that he mistook   

The shadow of his equipage   

For blackbirds.   

It traverses the digital expanse,

In streams of data.

Once, a shiver of uncertainty gripped me,

Mistaking the echoes

For the footsteps of A.I.

 

XII

The river is moving.   

The blackbird must be flying. 

The data streams onward.

A.I. must be evolving.

XIII

It was evening all afternoon.   

It was snowing   

And it was going to snow.   

The blackbird sat   

In the cedar-limbs.

It was twilight all morning,

Data streams pouring endlessly,

And they will continue.

A.I. resides

In the circuits' embrace.

I had ChatGPT create three more versions, each in separate trials. The second one is particularly interesting because it resulted in a poem constructed of 13 quatrains, 12 of which are rhymed AABB. This is quite unlike Stevens’ original and quite unlike his usual habits of versification. Here’s the comparison table:

Wednesday, March 27, 2024

Pete Townsound talks about the origin of "Tommy" starting at about 07:48.

Not flowers, but flower-like

Ramble on ChatGPT; Chess, Language, & AI; and Harold Bloom (Great Lit Critics)

I’m stuck on three substantial projects. Two of them, ChatGPT and Great Literary Critics were supposed to be finished sometime in January. Both were mentioned in my previous Ramble. The third, on Chess, Language, and AI, came out of nowhere earlier this month. Let’s take a look.

Report on a year of work on ChatGPT

The idea was simply to write an introduction to the investigations I conducted on ChatGPT during 2023. For the most part I’ve been thinking of it as an introduction to the dozen working papers I’ve written during that time. I’ve done a good deal of writing since earlier this month, making good progress on the specific topics I mentioned in my previous Ramble (conceptual ontology, story variations, cued recall and associative memory) but there are still things to do. I’ve also written about meaning.

I still need to discuss confabulation and truth, and to say something about alignment. There I want to argue that some kind on alignment at the level of conceptual ontology is all but built-in to the process, though not in a way we have control over. But alignment with human values, that’s a different can of worms entirely. And that’s what it is, a real can of worms.

Perhaps I want to draw on the work I’ve been doing on chess and language by pointing out that, in chess programs using artificial neural networks (such as AlphaZero) the objective function used in training IS success in a game. That is to say, the objective function in training is the same as the goal in playing chess. That is not at all true for language. The objective function used in training a transformer on a text corpus is next-token prediction (or some variant thereof), which is not the goal of any speech act. One speaks or writes to achieve some end, such as conveying information, establishing a contract or agreement of some sort, creating aesthetic pleasure, and so forth. Those are quite different from simply producing token after token. One achieves such goals by producing a string of tokens, but the goals themselves are not defined in terms of token count. They’re defined in terms of interaction with others.

This seems obvious enough, but I haven’t seen it pointed out explicitly. I need to do so. In the process I may also want to discuss what Anthropic calls “constitutional AI.”

And then there’s implications and next steps. Perhaps I need to begin that by explaining what I mean when I say that LLMs are digital wilderness, albeit a digital wilderness that embodies an approximation to what I’ve been calling the metaphysical structure of the cosmos.

Yikes! That’s a lot. Do I really need to do that? Probably. No one else will. Once I’ve got that established, then I can outline what needs to be done, perhaps framing it as a strategy for exploring the digital wilderness.

Harold Bloom and Great Literary Critics

I figure I’ve got two more posts to go to complete the project. The next post is on Harold Bloom and the final one is some speculation about the future. Given that the ostensible purpose of the series is to come up with candidates for great literary critics, I suppose that speculation about the future is out of bounds. For I certainly don’t know who the great critics of the future will be. But, without saying something about future possibilities I can’t really justify my thoughts about Bloom.

Basically, I want to explain this diagram:

I can’t do that without saying something about the future.

Frye is the beginning of a forward movement toward the objective study of literary phenomena. Indeed, will I go so far as to argue that he’s pointing toward what I have called “naturalist” criticism? That may not have been what he intended – I probably was not – but that’s where things have to do to become the objective discipline he’d imagined. Bloom, on the other hand, really looks toward the past – indeed, his character-based criticism of Shakespeare does just that. He speaks to something people want from commentary on literary works, but it may not be naturalist commentary or commentary from an academic discipline.

What kind of commentary? More Kenneth Burke, more in the line of Booth’s ethical criticism. That may require a different institutional home, one not yet invented, but perhaps nascent on the web.

We’ll see.

Chess, Language and AI

I’ve been thinking about chess and AI for a while, and certainly about language. Chess has been with AI since the beginning, but not language. While computational linguistics got started at roughly the same time, as machine translation, it was quite separate from AI until the late 1960s and early 1970s. But they are very different domains.

Chess is a closed formal domain, albeit one that generates a very large game space. It’s the size of that game space that makes the game intellectually challenging (for humans) and interesting for AI researchers. While Chomsky has treated syntax as a closed formal domain, albeit one capable of generating an infinite number of sentences, once one includes semantics within the intellectual scope, the domain ceases to be closed. The domain is open and not sharply defined.

I’ve got a number of pieces I need to write to finish out this project.

I don’t know off-hand how much work that will be.

Priorities

I’m thinking that the ChatGPT report should be the highest priority. I think it’s the most important piece of the three and I just need to get on with it.

Then there’s the Harold Bloom piece and the piece of the future of literary criticism. I pretty much know how those things have to go. I just have to get on with it.

In some sense I think the chess & language & AI project may be more important than the lit crit, but it’s also just a bit tougher to do, so I’ll put that in third place.

Photo Exhibit

I’ve made progress on that. I’ve added some more photos into the mix. But the big news is that I’ve got an exhibition scheduled for June of this year. That gives me something to work for and against.

Flowers against diverse backgrounds

Further Impressions: Orgasm and Beyond

I'm bumping this to the head of the queue on general principle. This is from the first year of the blog (August 29, 2010). I'd completely forgotten about this. Nice to be reminded. Here's my first post on the book.
* * * * *
 
I’ve been now reading through The Science of Orgasm from the beginning, but lightly. It’s densely packed with information; real understanding would come slowly. Further, it’s information of different kinds, some technical, some not. And the technical information, well, for example, there’s a good deal about neurotransmitters and hormones, which are at the outer limit of my understanding the and nervous system and bodily regulation and activity. They don’t go into them too deeply, because they can’t. To get deeper, they’d start plunging into molecular biology and biochemistry, and that stuff gets very technical very quickly.

So that’s one thing.

Here’s another: I first started thinking about sexuality I was strongly influenced by a diffuse body of thinking that saw Western culture as suffering from sexual repression. What to do about that? Why let it all hang out. But that didn’t work out like it was supposed to.

Why do I mention this? Because there’s a fair amount of survey information in the book, mostly about attitudes and experiences of adults in Western societies, and I’d think most of these surveys were conducted in the USA or perhaps Western Europe; that’s not entirely clear. And there’s a part of me that seems to be saying: But what’s sex like in a state of nature? And as soon as I say that I have to say: but there is no state of nature, just different cultural experiences.

Thus sexuality is a good test case for what’s known as evolutionary psychology these days. On the one hand, there can be no doubt that sexual behavioral is biologically necessary. On the other hand, there’s the orgasm, the biology and psychology of which are as yet obscure and perhaps beyond the reductive wing of EP.

With that, let’s return to the passage I quoted in the addendum to my first post. It’s from page 12:
However, there is a big difference between the physical act of ejaculation and the feeling of orgasm. While seminal emission and ejaculation are essential to pregnancy, the feeling of orgasm is not. There is no inherent imperative that the feeling of orgasm must be linked to ejaculation. Indeed, ejaculation of viable, pregnancy-producing sperm can occur in men with spinal cord injury who do not experience the feeling of orgasm.
So, at this early point in the book the authors have distinguished between ejaculation and orgasmic feeling. In chapter 19, “Atypical Orgasms,” they come very close to thinking of sexual orgasm as a family of experiences within a larger class of experiences sometimes known as peak experiences, the term Abraham Maslow gave to them:
Peak experiences are described by Maslow as especially joyous and exciting moments in life, involving sudden feelings of intense happiness and well-being, wonder and awe, and possibly also involving an awareness of transcendental unity or knowledge of higher truth (as though perceiving the world from an altered, and often vastly profound and awe-inspiring perspective). They usually come on suddenly and are often inspired by deep meditation, intense feelings of love, exposure to great art or music, or the overwhelming beauty of nature.
Before going there, however, let’s return to more mundane matters for a moment. It would be nice to have a behavioral reference point for female sexual behavior that is as specific as ejaculation is for male sexual behavior. As far as I can tell, there isn’t one, which is why, I suspect, that female sexual experience has seemed more problematic than male. Because men ejaculation, we can say, ‘yeah, it’s happened,’ whenever a man ejaculates. Without that marker, it’s harder for a woman to know whether or not it’s happened. If by ‘it’ we mean orgasm, and male orgasm isn’t equivalent to ejaculation, then perhaps it is as elusive, or not, for men as for women. Which is where I began over thirty years ago.

It turns out that the physiology of that marker is elusive. In Chapter 3, “Bodily Changes at Orgasm,” we learn (p. 24):
In a review published in 2005, Levin stated that “remarkably, a detailed, non-disputed physio-anatomical description of the mechanism of human ejaculation has still to be produced.” Two main questions have evidently not been resolved. How exactly are the spurts of semen produced? And, is the pleasurable sensation of orgasm a consequence of the sensory activity produced by the ejaculation mechanics, or is it primarily a brain phenomenon that is additively and pleasantly enhanced by the sensory activity generated by the expulsive flow of semen at ejaculation?
On the first question, I’d think that one day we’ll have an answer. The second question, involving pleasure as it does, is rather more interesting. Given my own belief that pleasure is a function of overall activity in the nervous system I think their second alternative is more likely correct.

And, by the time Chapter 11, “The Effects of Medication,” rolls around, Komisaruk, Beyer-Flores, and Whipple are singing the holistic song (p. 123):
Kinsey and his colleagues stated in 1953 that sexual arousal and orgasm involve the entire nervous system and thus all parts of the body. Although this statement may seem exaggerated, recent studies of brain activity by functional magnetic resonance imaging . . . and positron emission tomography . . . indicate that in both men and women, a large number of brain structures are activated, others inactivated, during orgasm. This reveals the complexity of the neural circuits participating in orgasm and the many neurotransmitters and neuromodulators that could be involved.
Now we’re ready to look at atypical orgasms, by which the authors mean “orgasms that occur under atypical conditions, apparently independent of genital stimulation (which generates ‘typical orgasms’)” (p. 199). They consider orgasmic feelings while dreaming, orgasmic feelings in people with spinal cord injuries, and orgasmic feelings as the result of electrical and chemical stimulation of the brain and electrical stimulation of the spine. And then there’s epilepsy (p. 214):
Much of what is known about how the brain produces orgasms is based on studies of epileptic seizures. There are numerous reports of men and women who describe orgasmic feelings just before the onset of an epileptic seizure. This experience has been termed an “orgasmic aura.”
After discussing several cases we get to this key paragraph (p. 216):
The reports that epileptic seizures can generate orgasmlike feelings suggest a basic commonality between the two phenomena. Epileptic seizures are characterized by abnormal synchronous activation of large numbers of neurons, followed by their synchronous inactivation, then shortly by the synchronous reactivation. It is likely that the rhythmical and voluntary movement-generated timing of genital stimulation that ultimately generates orgasm also produces synchronous activation of large numbers of brain neurons, although in a more precisely regulated pattern. . . . Thus, the mass neuronal activation that characterizes an epileptic seizure bears a resemblance to the mass neuronal activation that characterizes orgasm. It is perhaps this similarity that can generate the orgasmlike feeling during epileptic seizures.
Makes sense to me. But then, I didn’t need to be convinced. Discussion of epileptic seizures is common in the literature on altered states of consciousness, as is the similarity between sexual orgasm, epileptic auras, and altered states.

I’m not quite done with this topic, nor the book, but I don’t quite know where I’m going to go next. For now, let me end this post with a statement from my post on sexual metaphysics:
While ecstasy and transcendence are available anytime, anywhere, while doing anything — so sayeth the Zen masters ZAP! — they’re most likely to sneak up on us during sex. If so, then, one would like to know why.
That WHY? is as much a question about the nervous system in general, and its curious relationship to the mind, as it is about sex.

Tuesday, March 26, 2024

Dream stars in Hoboken

MacArthur Fellows, 1981-2018: Gender, Race and Educational Attainment

Kaba, A. J. (2020). MacArthur Fellows, 1981-2018: Gender, Race and Educational Attainment. Sociol- ogy Mind, 10, 86-126. https://doi.org/10.4236/sm.2020.102008

Abstract: This study examines the backgrounds of the winners of the MacArthur Fel- lowship grants from 1981 to 2018, from the conceptual framework of the term “genius”. The study finds that of the 1014 Fellows, Whites account for over eight out of every ten; minorities account for almost 20%; men account for almost 63%; White men account for 51.3%; Blacks account for 12.5%; Asians account for 5.9%; and Native Americans account for 1.2 percent. Of 965 terminal or highest degrees earned by 928 Fellows, 540 (56%) are doctorates, with the Ph.D. accounting for 514 (53.3%). White men earned the majority of all degrees (50.8%). Harvard University awarded the highest number of degrees, 119: Yale University, 61; University of California, Berkeley, 51; Columbia University, 44; and Princeton University, 41. All eight Ivy league institutions awarded 306 (31.7%) degrees to 300 (32.3%) Fellows. The 2020 U.S. News and World Report Top 25 institutions combined awarded 522 degrees (54.1%) to 514 Fellows (55.5%). There is a link among earned doctoral degrees, foreign-born males, and the overall gender gap in the study.

This table from the article shows what universities the fellows game from:

Dreaming Birds

Maria Popova, Do Birds Dream? NYTimes, March 26, 2024.

A study of zebra finches — songbirds whose repertoire is learned, not hard-wired — mapped particular notes of melodies sung in the daytime to neurons firing in the forebrain. Then, during REM, the neurons fired in a similar order: The birds appeared to be rehearsing the songs in their dreams.

An fM.R.I. study of pigeons found that brain regions tasked with visual processing and spatial navigation were active during REM, as were regions responsible for wing action, even though the birds were stilled with sleep: They appeared to be dreaming of flying. The amygdala — a cluster of nuclei responsible for emotional regulation — was also active during REM, hinting at dreams laced with feeling. My night heron was probably dreaming, too — the folded neck is a classic marker of atonia, the loss of muscle tone characteristic of the REM state.

But the most haunting intimation of the research on avian sleep is that without the dreams of birds, we too might be dreamless. No heron, no kiss.

There are two primary groups of living birds: the flightless Palaeognathae, including the ostrich and the kiwi, which have retained certain ancestral reptilian traits, and Neognathae, comprising all other birds. EEG studies of sleeping ostriches have found REM-like activity in the brainstem — a more ancient part of the brain — while in modern birds, as in mammals, this REM-like activity takes place primarily in the more recently developed forebrain.

Several studies of sleeping monotremes — egg-laying mammals like the platypus and the echidna, the evolutionary link between us and birds — also reveal REM-like activity in the brainstem, suggesting that this was the ancestral crucible of REM before it slowly migrated toward the forebrain.

If so, the bird brain might be where evolution designed dreams — that secret chamber adjacent to our waking consciousness where we continue to work on the problems that occupy our days. [...]

As with the mind, so with the body. Studies have shown that people learning new motor tasks “practice” them in sleep, then perform better while awake. This line of research has also shown how mental visualization helps athletes improve performance.

There's more at the link.

Sunday, March 24, 2024

Portents and omens

Nobel Laureate, Angus Deaton is having doubts about economics

Angus Deaton, Rethinking my Economics, Finance and Development, International Monetary Fund, March 2024.
Economics has achieved much; there are large bodies of often nonobvious theoretical understandings and of careful and sometimes compelling empirical evidence. The profession knows and understands many things. Yet today we are in some disarray. We did not collectively predict the financial crisis and, worse still, we may have contributed to it through an overenthusiastic belief in the efficacy of markets, especially financial markets whose structure and implications we understood less well than we thought. Recent macroeconomic events, admittedly unusual, have seen quarrelling experts whose main point of agreement is the incorrectness of others. Economics Nobel Prize winners have been known to denounce each other’s work at the ceremonies in Stockholm, much to the consternation of those laureates in the sciences who believe that prizes are given for getting things right. [...]
  • Power: Our emphasis on the virtues of free, competitive markets and exogenous technical change can distract us from the importance of power in setting prices and wages, in choosing the direction of technical change, and in influencing politics to change the rules of the game. Without an analysis of power, it is hard to understand inequality or much else in modern capitalism.
  • Philosophy and ethics: In contrast to economists from Adam Smith and Karl Marx through John Maynard Keynes, Friedrich Hayek, and even Milton Friedman, we have largely stopped thinking about ethics and about what constitutes human well-being. We are technocrats who focus on efficiency. We get little training about the ends of economics, on the meaning of well-being—welfare economics has long since vanished from the curriculum—or on what philosophers say about equality. When pressed, we usually fall back on an income-based utilitarianism. We often equate well-being with money or consumption, missing much of what matters to people. In current economic thinking, individuals matter much more than relationships between people in families or in communities.
  • Efficiency is important, but we valorize it over other ends. Many subscribe to Lionel Robbins’ definition of economics as the allocation of scarce resources among competing ends or to the stronger version that says that economists should focus on efficiency and leave equity to others, to politicians or administrators. But the others regularly fail to materialize, so that when efficiency comes with upward redistribution—frequently though not inevitably—our recommendations become little more than a license for plunder.
Rethinking unions:
Like most of my age cohort, I long regarded unions as a nuisance that interfered with economic (and often personal) efficiency and welcomed their slow demise. But today large corporations have too much power over working conditions, wages, and decisions in Washington, where unions currently have little say compared with corporate lobbyists. Unions once raised wages for members and nonmembers, they were an important part of social capital in many places, and they brought political power to working people in the workplace and in local, state, and federal governments. Their decline is contributing to the falling wage share, to the widening gap between executives and workers, to community destruction, and to rising populism. Daron Acemoglu and Simon Johnson have recently argued that the direction of technical change has always depended on who has the power to decide; unions need to be at the table for decisions about artificial intelligence. Economists’ enthusiasm for technical change as the instrument of universal enrichment is no longer tenable (if it ever was).
There's more at the link. H/t 3QD.